rippled/.github/workflows/telemetry-validation.yml

# Telemetry Validation CI Workflow
#
# Builds rippled with telemetry enabled, runs the multi-node workload
# harness, validates all telemetry data, and runs performance benchmarks.
#
# This is a separate workflow from the main CI. It runs:
#   - On manual dispatch (workflow_dispatch)
#   - On pushes to telemetry-related branches
#
# The workflow is intentionally heavyweight (builds rippled, starts Docker
# services, runs a multi-node cluster) — it validates the full telemetry
# stack end-to-end rather than individual unit tests.

name: Telemetry Validation

on:
  workflow_dispatch:
    inputs:
      rpc_rate:
        description: "RPC load rate (requests per second)"
        required: false
        default: "50"
      rpc_duration:
        description: "RPC load duration (seconds)"
        required: false
        default: "120"
      tx_tps:
        description: "Transaction submit rate (TPS)"
        required: false
        default: "5"
      tx_duration:
        description: "Transaction submit duration (seconds)"
        required: false
        default: "120"
      run_benchmark:
        description: "Run performance benchmarks"
        required: false
        type: boolean
        default: false

  push:
    branches:
      - "pratik/otel-phase*"
      - "feature/otel-*"
      - "feature/telemetry-*"
    paths:
      - "docker/telemetry/**"
      - "include/xrpl/basics/Telemetry*.h"
      - "src/xrpld/app/misc/Telemetry*"

concurrency:
  group: telemetry-validation-${{ github.ref }}
  cancel-in-progress: true

jobs:
  validate-telemetry:
    name: Telemetry Stack Validation
    runs-on: ubuntu-latest
    timeout-minutes: 60

    services:
      # Docker-in-Docker not needed — we use docker compose directly.
      # The runner has Docker pre-installed.
      docker:
        image: docker:dind
        options: --privileged

    steps:
      - name: Checkout repository
        uses: actions/checkout@v4

      - name: Install system dependencies
        run: |
          sudo apt-get update
          sudo apt-get install -y curl jq bc python3 python3-pip

      - name: Install Python dependencies
        run: pip3 install -r docker/telemetry/workload/requirements.txt

      - name: Install Conan
        run: pip3 install conan

      - name: Set up Conan
        uses: ./.github/actions/setup-conan

      - name: Cache Conan packages and build directory
        uses: actions/cache@v4
        with:
          path: |
            ~/.conan2/p
            .build
          key: telemetry-build-${{ runner.os }}-${{ hashFiles('conanfile.py', 'CMakeLists.txt') }}
          restore-keys: |
            telemetry-build-${{ runner.os }}-

      - name: Build rippled with telemetry
        run: |
          conan install . \
            --profile ci \
            --build=missing \
            --settings:all build_type=Release
          cmake \
            -B build \
            -G Ninja \
            -DCMAKE_TOOLCHAIN_FILE:FILEPATH=build/generators/conan_toolchain.cmake \
            -DCMAKE_BUILD_TYPE=Release \
            -Dtelemetry=ON
          cmake --build build --target xrpld --parallel $(nproc)

      - name: Make scripts executable
        run: |
          chmod +x docker/telemetry/workload/*.sh

      - name: Run full telemetry validation
        id: validation
        env:
          XRPLD: build/xrpld
        run: |
          ARGS="--xrpld build/xrpld --skip-loki"
          ARGS="$ARGS --rpc-rate ${{ github.event.inputs.rpc_rate || '50' }}"
          ARGS="$ARGS --rpc-duration ${{ github.event.inputs.rpc_duration || '120' }}"
          ARGS="$ARGS --tx-tps ${{ github.event.inputs.tx_tps || '5' }}"
          ARGS="$ARGS --tx-duration ${{ github.event.inputs.tx_duration || '120' }}"
          if [ "${{ github.event.inputs.run_benchmark }}" = "true" ]; then
            ARGS="$ARGS --with-benchmark"
          fi
          docker/telemetry/workload/run-full-validation.sh $ARGS
        continue-on-error: true

      - name: Upload validation reports
        if: always()
        uses: actions/upload-artifact@v4
        with:
          name: telemetry-validation-reports
          path: /tmp/xrpld-validation/reports/
          retention-days: 30

      - name: Upload node logs
        if: failure()
        uses: actions/upload-artifact@v4
        with:
          name: xrpld-node-logs
          path: /tmp/xrpld-validation/node*/debug.log
          retention-days: 7

      - name: Print validation summary
        if: always()
        run: |
          REPORT="/tmp/xrpld-validation/reports/validation-report.json"
          if [ -f "$REPORT" ]; then
            echo "## Telemetry Validation Results" >> "$GITHUB_STEP_SUMMARY"
            echo "" >> "$GITHUB_STEP_SUMMARY"
            TOTAL=$(jq '.summary.total' "$REPORT")
            PASSED=$(jq '.summary.passed' "$REPORT")
            FAILED=$(jq '.summary.failed' "$REPORT")
            echo "| Metric | Value |" >> "$GITHUB_STEP_SUMMARY"
            echo "|--------|-------|" >> "$GITHUB_STEP_SUMMARY"
            echo "| Total Checks | $TOTAL |" >> "$GITHUB_STEP_SUMMARY"
            echo "| Passed | $PASSED |" >> "$GITHUB_STEP_SUMMARY"
            echo "| Failed | $FAILED |" >> "$GITHUB_STEP_SUMMARY"
            echo "" >> "$GITHUB_STEP_SUMMARY"
            if [ "$FAILED" -gt 0 ]; then
              echo "### Failed Checks" >> "$GITHUB_STEP_SUMMARY"
              echo "" >> "$GITHUB_STEP_SUMMARY"
              jq -r '.checks[] | select(.passed == false) | "- **\(.name)**: \(.message)"' "$REPORT" >> "$GITHUB_STEP_SUMMARY"
            fi
          fi

      - name: Cleanup
        if: always()
        run: |
          docker/telemetry/workload/run-full-validation.sh --cleanup 2>/dev/null || true

      - name: Check validation result
        if: steps.validation.outcome == 'failure'
        run: |
          echo "Telemetry validation failed. Check the uploaded reports for details."
          exit 1